TY  - CONF
Y1  - 2015///
AV  - public
M2  - Quebec City, Canada
A1  - Vidal, Esteban
A1  - Piotto, Nicola
A1  - Cordara, Giovanni
A1  - Morán Burgos, Francisco
SN  - 1522-4880
KW  - 3D Reconstruction
KW  -  SfM
KW  -  Video Registration
KW  -  Point Cloud Alignment
PB  - IEEE
N2  - In Structure-from-Motion (SfM) applications, the capability of integrating new visual information into existing 3D models is an important need. In particular, video streams could bring significant advantages, since they provide dense and redundant information, even if normally only relative to a limited portion of the scene. In this work we propose a fast technique to reliably integrate local but dense information from videos into existing global but sparse 3D models. We show how to extract from the video data local 3D information that can be easily processed allowing incremental growing, refinement, and update of the existing 3D models. The proposed technique has been tested against two state-of-the-art SfM algorithms, showing significant improvements in terms of computational time and final point cloud density.
TI  - Automatic video to point cloud registration in a structure-from- motion framework
ID  - upm41384
T2  - International Conference on Image Processing (ICIP 2015)
UR  - http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7351282
EP  - 2650
SP  - 2646
ER  -